Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    i
    1.56
    de
    1.45
    ست
    1.32
    า
    1.30
    :
    1.30
    -
    1.28
    na
    1.24
    י
    1.23
    ni
    1.20
    ي
    1.20
    POSITIVE LOGITS
    이었
    1.28
     imao
    1.23
     zacz
    1.20
     istraž
    1.20
    િ
    1.19
    டன்
    1.17
    цима
    1.16
     agreg
    1.09
     važ
    1.09
     añad
    1.08
    Act Density 0.000%

    No Known Activations